Abstract
Current assembly process planning of complex products depends mainly on existing process templates and the experience of technical personnel, resulting in low design efficiency, poor process pertinence, low intelligence, and difficulty to extract the assembly knowledge. To address these problems, this paper proposes an intelligent decision-making system for complex products assembly process planning based on the machine learning (ML) method, providing a targeted decision-making scheme with an assembly process structure tree. The characteristics, variations, and similarities of the assembly process for complex products were analyzed. A hierarchical model of the product assembly process is established, based on which the assembly process decision-making for overall structure is decomposed into several units. Then, an intelligent decision-making model for new product assembly process planning was constructed through ML by considering the variability of component composition of different product models and existing product assembly data. Based on these, an optimized decision-making model was established through a swarm intelligence algorithm that automatically optimizes the initial weight, threshold, learning rate, and feedback process, improving the decision efficiency and accuracy of system. To validate the system, the intelligent decision-making assembly process was conducted on a cylinder cap as a case study, and the system capability is discussed in terms of ML performance and industrial applicability.
Similar content being viewed by others
Availability of data and material
The datasets used or analyzed during the current study are partial available from the corresponding author on reasonable request.
Code availability
The code is partial available from the corresponding author on reasonable request.
References
Gruhier E, Demoly F, Gomes S (2017) A spatiotemporal information management framework for product design and assembly process planning reconciliation. Comput Ind 90:17–41. https://doi.org/10.1016/j.compind.2017.04.004
Bikas C, Argyrou A, Pintzos G, Giannoulis C, Sipsas K, Papakostas N (2016) An automated assembly process planning system Procedia CIRP 44:222–227. https://doi.org/10.1016/j.procir.2016.02.085
Xu L, Li Y, Xu N, Hu Y, Wang C, He J, Cao Y, Chen S, Li D (2014) Soy sauce classification by geographic region and fermentation based on artificial netural network and genetic algorithm. J Agric Food Chem 62(51):12294–12298. https://doi.org/10.1021/jf504530w
Yaïci W, Entchcv E (2014) Performance prediction of a solar thermal energy system using artificial neural networks. Appl Therm Eng 73(1):1348–1359. https://doi.org/10.1016/j.applthermaleng.2014.07.040
Savich A, Moussa M, Areibi S (2012) A scalable pipelined architecture for real-time computation of MLP-BP neural networks. Microprocess Microsyst 36(2):138–150. https://doi.org/10.1016/j.micpro.2010.12.001
Zhang H, Fei T, Guan W, Zhang S, Jin Z, Tang W (2017) Research on visual 3d assembly process design and simulation for marine diesel engine. Clust Comput 2:1–15. https://doi.org/10.1007/s10586-017-1342-1
Saivaew N, Butdee S (2020) Decision making for effective assembly machined parts selection using fuzzy ahp and fuzzy logic. Mater Today. https://doi.org/10.1016/j.matpr.2020.02.491
Yi Y, Yan Y, Liu X, Ni Z, Feng J, Liu J (2021) Digital twin-based smart assembly process design and application framework for complex products and its case study. J Manuf Syst 58:94–107. https://doi.org/10.1016/j.jmsy.2020.04.013
Tsutsumi D, Gyulai D, Kovács A, Tipary B, Ueno Y, Nonaka Y, Monostory L (2018) Towards joint optimization of product design, process planning and production planning in multi-product assembly. Crip Annals. https://doi.org/10.1016/j.cirp.2018.04.036
Krist K, Sievers T, Onken A, Kodjo Y, Tracht K (2020) Application of derivative products for integrating expert knowledge into assembly process planning. Procedia CIRP 88:88–93. https://doi.org/10.1016/j.procir.2020.05.016
Chen J, Jia X (2020) An approach for assembly process case discovery using multimedia information source. Comput Ind 115(1):103176. https://doi.org/10.1016/j.compind.2019.103176
Lu C, Li J (2017) Assembly sequence planning considering the effect of assembly resources with a discrete fireworks algorithm. Int J Adv Manuf Technol. https://doi.org/10.1007/s00170-017-0663-9
Zhang H, Peng Q, Zhang J, Gu P (2021) Planning for automatic product assembly using reinforcement learning. Comput Ind 130(2):103471. https://doi.org/10.1016/j.compind.2021.103471
Qian J, Zhang Z, Shao C, Gong H, Liu D (2021) Assembly sequence planning method based on knowledge and ontostep. Procedia CIRP 97(1):502–507. https://doi.org/10.1016/j.procir.2020.05.266
Hou W, Li X, Jin Y, Wu J (2008) A study of intelligent decision-making system based on neural networks and expert system. International Conference on Cyberworlds. IEEE Computer Society
Ahmad R, Tichadou S, Hascoet J (2016) A knowledge-based intelligent decision system for production planning. Int J Adv Manuf Technol 89(5–8):1717–1729. https://doi.org/10.1007/s00170-016-9214-z
Simeone A, Zeng Y, Caggiano A (2020) Intelligent decision-making support system for manufacturing solution recommendation in a cloud framework. Int J Adv Manuf Technol (1). https://doi.org/10.1007/s00170-020-06389-1
Burggräf P, Wagner J, Koke B, Bamberg M (2020) Performance assessment methodology for AI-supported decision-making in production management. 53rd CIRP Conference on Manufacturing Systems 2020
Teixeira M, Maran V, Oliveira J, Winter M, Machado A (2019) Situation-aware model for multi-objective decision making in ambient intelligence. Appl Soft Comput. https://doi.org/10.1016/j.asoc.2019.105532
Mahmoodzadeh A, Mohammadi M, Daraei A, Faraj R, Omer R, Sherwani A (2020) Decision-making in tunneling using artificial intelligence tools. Tunn Undergr Space Technol 103:103514. https://doi.org/10.1016/j.tust.2020.103514
Zhao X, Wang C, Su J, Wang J (2019) Research and application based on the swarm intelligence algorithm and artificial intelligence for wind farm decision system. Renew Energy 134(APR):681–697. https://doi.org/10.1016/j.renene.2018.11.061
Bettinelli M, Occello M, Genthial D, Brissaud D (2020) A decision support framework for remanufacturing of highly variable products using a collective intelligence approach. Procedia CIRP 90:594–599. https://doi.org/10.1016/j.procir.2020.06.003
Han X, Xiong X, Duan F (2015) A new method for image segmentation based on BP neural network and gravitational search algorithm enhanced by cat chaotic mapping. Appl Intell 43(4):855–873. https://doi.org/10.1007/s10489-015-0679-5
Liu Y, Xie F, Xie C, Peng M, Wu G, Xia H (2015) Prediction of time series of NPP operating parameters using dynamic model based on BP neural network. Ann Nucl Energy 85(NOV):566–575. https://doi.org/10.1016/j.anucene.2015.06.009
Mirjalili S (2015) The ant lion optimizer. Adv Eng Softw 83:80–98. https://doi.org/10.1016/j.advengsoft.2015.01.010
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design. Sheng-Wen Zhang: supervision, method design, review. Zhan Wang: method design, programming, data collection and analysis, writing - original draft. De-Jun Cheng: supervision, method design, review, editing. Xi-Feng Fang: method design, review.
Corresponding authors
Ethics declarations
Ethics approval
Not applicable.
Consent to participate
Not applicable.
Consent for publication
Written informed consent for publication was obtained from all participants.
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zhang, SW., Wang, Z., Cheng, DJ. et al. An intelligent decision-making system for assembly process planning based on machine learning considering the variety of assembly unit and assembly process. Int J Adv Manuf Technol 121, 805–825 (2022). https://doi.org/10.1007/s00170-022-09350-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-022-09350-6